Perspective Distortion Modeling, Learning and Compensation

被引：0
|
作者：
Valente, Joachim [1 ]
Soatto, Stefano [2 ]
机构：
[1] Google, Mountain View, CA 94043 USA
[2] Univ Calif Los Angeles, UCLA Vis Lab, Los Angeles, CA USA
来源：
2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) | 2015年
关键词：
FACE-RECOGNITION;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We describe a method to model perspective distortion as a one-parameter family of warping functions. This can be used to mitigate its effects on face recognition, or synthesis to manipulate the perceived characteristics of a face. The warps are learned from a novel dataset and, by comparing one-parameter families of images, instead of images themselves, we show the effects on face recognition, which are most significant when small focal lengths are used. Additional applications are presented to image editing, video conference, and multi-view validation of recognition systems.
引用
收藏
页数：8
相关论文
共 50 条
  • [31] Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective
    Li, Xin
    Li, Bingchen
    Jin, Xin
    Lan, Cuiling
    Chen, Zhibo
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR, 2023, : 1714 - 1724
  • [32] Deep Learning-based Face Recognition and the Robustness to Perspective Distortion
    Damer, Naser
    Wainakh, Yaza
    Henniger, Olaf
    Croll, Christian
    Berthe, Benoit
    Braun, Andreas
    Kuijper, Arjan
    2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 3445 - 3450
  • [33] Distortion and instability compensation with deep learning for rotational scanning endoscopic optical coherence tomography
    Liao, Guiqiu
    Caravaca-Mora, Oscar
    Rosa, Benoit
    Zanne, Philippe
    Dall'Alba, Diego
    Fiorini, Paolo
    de Mathelin, Michel
    Nageotte, Florent
    Gora, Michalina J.
    MEDICAL IMAGE ANALYSIS, 2022, 77
  • [34] Reinforcement learning and dopamine in the striatum: A modeling perspective
    Wanjerkhede, Shesharao M.
    Bapi, Raju S.
    Mytri, Vithal D.
    NEUROCOMPUTING, 2014, 138 : 27 - 40
  • [35] A perspective on machine learning methods in turbulence modeling
    Beck A.
    Kurz M.
    GAMM Mitteilungen, 2021, 44 (01)
  • [36] A Perspective on Deep Learning for Molecular Modeling and Simulations
    Zhang, Jun
    Lei, Yao-Kun
    hZang, Zhen
    Chang, Junhan
    Li, Maodong
    Han, Xu
    Yang, Lijiang
    Yang, Yi Isaac
    Gao, Yi Qin
    JOURNAL OF PHYSICAL CHEMISTRY A, 2020, 124 (34): : 6745 - 6763
  • [37] MATHEMATICAL-MODELING OF LIGHT-BEAM DISTORTION COMPENSATION SYSTEM BY FLEXIBLE AND SEGMENTED MIRRORS
    SUKHORUKOV, AP
    TROFIMOV, VA
    IZVESTIYA AKADEMII NAUK SSSR SERIYA FIZICHESKAYA, 1988, 52 (02): : 377 - 382
  • [38] A Digital Modeling Technique for Distortion Effect Based on a Machine Learning Approach
    Matsunaga, Yuto
    Aoki, Naofumi
    Dobashi, Yoshinori
    Yamamoto, Tsuyoshi
    2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 1888 - 1892
  • [39] Distortion Compensation in Structured Lighting Systems
    Guzhov, Vladimir, I
    Ilinykh, Sergey P.
    Trubilina, Ekaterina E.
    2020 1ST INTERNATIONAL CONFERENCE PROBLEMS OF INFORMATICS, ELECTRONICS, AND RADIO ENGINEERING (PIERE), 2020, : 277 - 280
  • [40] Optimal distortion compensation for quantization watermarking
    Staring, M
    Oostveen, J
    Kalker, T
    2003 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL 2, PROCEEDINGS, 2003, : 727 - 730
12345